• 전자공학회논문지
• /
• 제50권10호
• /
• pp.150-161
• /
• 2013

본 논문에서는 다수의 카메라들을 이용하여 3차원 공간상에 있는 물체에 대한 다중 시점 영상들을 획득하고, 그 영상들로부터 해당 3차원 물체에 대한 기하학적인 형상 및 질감 정보를 추정하여, 그 물체에 대한 고해상도 3차원 콘텐츠를 효율적으로 제작하는 새로운 시스템을 제안한다. 지금까지 다양한 다중 시점 영상 기반 3차원 객체 복원 시스템들이 제안되었지만 다중 시점 기반 3차원 객체 복원이 많은 메모리와 계산량을 필요로 하기 때문에 고해상도의 3차원 콘텐츠를 얻는 데에는 어려움이 있었다. 3차원 복원에 필요한 계산량 및 메모리량을 줄이기 위해 제안 시스템은 객체의 다중 시점을 촬영한 영상 내에서 객체가 존재할 수 있는 영역을 사전에 설정하여 객체 윤곽선 추출 과정을 빠르게 수행한다. 그리고 체인코드를 활용하여 실루엣 영상을 표현하고 3차원-2차원 투영 및 역투영 관계를 1차원 호모그래피를 통해 표현하여 객체의 비주얼 헐을 빠르게 계산한다. 복원된 3차원 객체의 기하정보는 3차원 선분 기반의 표현 기법인 DoCube를 활용하여 적은 데이터양으로 표현하였으며, 3차원 메시 생성 및 텍스쳐 맵핑을 수행하여 최종적인 3차원 객체를 생성한다. 실험 결과 제안 시스템이 $800{\times}800{\times}800$ 해상도의 3차원 객체 복원을 프레임 당 2.2초에 수행하는 것을 확인하였다.

• 방송공학회논문지
• /
• 제25권1호
• /
• pp.1-12
• /
• 2020

의료분야에서 질환별 유병률 차이로 인한 데이터 수적 불균형은 흔하게 발생되는 문제로 인공지능 학습 성능을 저하시켜 개발의 어려움을 초래한다. 최근 이러한 데이터 수적 불균형문제를 해결하기 위한 한 방법으로 적대적 생성 신경망(GAN) 기술이 도입되었고 다양한 분야에 성공적으로 적용되어왔다. 그러나 수적 불균형에 의해 저하된 성능 문제를 해결하는데 있어서 기존 연구들의 영상 해상도가 아직 충분하지 않고 영상 내 구조가 전역적으로 일관성 있게 모델링 되지 않아 좋은 결과를 얻기 어렵다. 본 논문에서는, 흉부 X선 영상 데이터의 수적 불균형문제를 해결하기 위하여 고해상도 영상을 생성할 수 있는 주목 메커니즘 기반 멀티 스케일 조건부 적대적 생성 네트워크를 제안한다. 해당 네트워크는 질환제어 조건변수에 의해 하나의 네트워크만으로 다양한 질환 영상을 생성할 수 있어 각 클래스별로 학습을 하는 비효율성을 줄였고, 자기 주목 메커니즘을 통해 영상 내 장거리 종속성 문제를 해결하였다.

• 한국해안해양공학회:학술대회논문집
• /
• 한국해안해양공학회 2003년도 한국해안해양공학발표논문집
• /
• pp.164-169
• /
• 2003

The need fur higher grid resolution in climate models is often discussed (e.g. McAvaney et al.,2001) because a number of important oceanic processes are not resolved by the current generation of coupled models, e.g., boundary currents, mesoscale eddy fluxes, sill through flows. McClean et al., (1997) and Bryan and Smith (1998) have compared simulated mesoscale variability in simulations at several eddy-resolving resolutions to TOPEX/Poseidon and similar data. (omitted)

• 한국해양공학회지
• /
• 제31권6호
• /
• pp.405-412
• /
• 2017

Because of the rapid development of computer technology in recent years, wave models can utilize parallel calculations for the high-resolution prediction of open sea and coastal areas with high accuracy. Parallel calculations also allow national agencies in the relevant sectors to produce marine forecasting data through massive parallel calculations. Meanwhile, the eastern coast of the Korean Peninsula has been increasingly damaged by swell-like high waves, and many researchers and scientists are continuing their efforts to anticipate and reduce the damage. In general, the short-term transformation of swell-like high waves can be reproduced relatively well in the third generation wave models, but the transformation of relatively long period waves needs to be simulated with higher accuracy in terms of the nonlinear wave interactions to gain a better understanding of the low-frequency wave generation and development mechanisms. In this study, we developed a calculation module to improve the calculation of the nonlinear energy transfer in the 3rd generation wave model and integrated it into the wave model to effectively consider the nonlinear wave interaction. First, the nonlinear energy transfer calculation module and third generation model were combined. Then, the combined model was used to reproduce the wave transformation due to the nonlinear interaction, and the performance of the developed operation module was verified.

• 한국측량학회지
• /
• 제36권3호
• /
• pp.135-152
• /
• 2018

The purpose of this study is to propose an optimal fusion method of aerial multi - sensor data to improve the accuracy of land cover classification. Recently, in the fields of environmental impact assessment and land monitoring, high-resolution image data has been acquired for many regions for quantitative land management using aerial multi-sensor, but most of them are used only for the purpose of the project. Hyperspectral sensor data, which is mainly used for land cover classification, has the advantage of high classification accuracy, but it is difficult to classify the accurate land cover state because only the visible and near infrared wavelengths are acquired and of low spatial resolution. Therefore, there is a need for research that can improve the accuracy of land cover classification by fusing hyperspectral sensor data with multispectral sensor and aerial laser sensor data. As a fusion method of aerial multisensor, we proposed a pixel ratio adjustment method, a band accumulation method, and a spectral graph adjustment method. Fusion parameters such as fusion rate, band accumulation, spectral graph expansion ratio were selected according to the fusion method, and the fusion data generation and degree of land cover classification accuracy were calculated by applying incremental changes to the fusion variables. Optimal fusion variables for hyperspectral data, multispectral data and aerial laser data were derived by considering the correlation between land cover classification accuracy and fusion variables.

• 한국해양공학회지
• /
• 제35권4호
• /
• pp.273-286
• /
• 2021

In recent years, as human casualties and property damage caused by hazardous waves have increased in the East Sea, precise wave prediction skills have become necessary. In this study, the Simulating WAves Nearshore (SWAN) third-generation numerical wave model was calibrated and optimized to enhance the accuracy of winter storm wave prediction in the East Sea. We used Source Term 6 (ST6) and physical observations from a large-scale experiment conducted in Australia and compared its results to Komen's formula, a default in SWAN. As input wind data, we used Korean Meteorological Agency's (KMA's) operational meteorological model called Regional Data Assimilation and Prediction System (RDAPS), the European Centre for Medium Range Weather Forecasts' newest 5th generation re-analysis data (ERA5), and Japanese Meteorological Agency's (JMA's) meso-scale forecasting data. We analyzed the accuracy of each model's results by comparing them to observation data. For quantitative analysis and assessment, the observed wave data for 6 locations from KMA and Korea Hydrographic and Oceanographic Agency (KHOA) were used, and statistical analysis was conducted to assess model accuracy. As a result, ST6 models had a smaller root mean square error and higher correlation coefficient than the default model in significant wave height prediction. However, for peak wave period simulation, the results were incoherent among each model and location. In simulations with different wind data, the simulation using ERA5 for input wind datashowed the most accurate results overall but underestimated the wave height in predicting high wave events compared to the simulation using RDAPS and JMA meso-scale model. In addition, it showed that the spatial resolution of wind plays a more significant role in predicting high wave events. Nevertheless, the numerical model optimized in this study highlighted some limitations in predicting high waves that rise rapidly in time caused by meteorological events. This suggests that further research is necessary to enhance the accuracy of wave prediction in various climate conditions, such as extreme weather.

• 한국통신학회논문지
• /
• 제37권4A호
• /
• pp.239-249
• /
• 2012

최근 자연스러운 3차원 영상의 재현을 위하여 깊이영상을 이용한 영상합성 방법이 널리 이용되고 있다. 깊이영상은 시청자의 눈에 보이지는 않지만 합성영상의 화질을 결정하는 중요한 정보이므로 정확한 깊이영상을 획득하는 것이 중요하다. 특히 적외선 센서를 이용한 깊이 카메라(time-of-flight camera)는 보다 정확한 깊이영상을 획득하는데 이용되고 있다. 깊이 카메라는 스테레오 정합(stereo matching)에 비해 정확하고 실시간으로 깊이정보를 추출할 수 있지만, 제공되는 해상도가 너무 낮다는 단점이 있다. 본 논문에서는 단시점의 깊이영상을 두 시점의 깊이영상으로 확장하고, 이를 이용하여 여러 시점의 중간영상을 생성하는 시스템을 제안한다. 특히 복잡도를 낮춰 빠른 속도로 다시점 영상을 생성하는 시스템을 제안한다. 고해상도의 컬러 영상을 획득하기 위하여 두 대의 컬러 카메라를 설치하고 중간에 깊이 카메라를 획득한다. 그리고 깊이 카메라에서 획득한 깊이영상을 3차원 워핑을 이용하여 양쪽의 컬러 카메라의 위치로 시점 이동한다. 깊이영상과 컬러영상간의 객체 불일치 문제는 깊이값의 신뢰 도를 기반으로 한 조인트 양방향 필터(joint bilateral filter)를 이용하여 보정한다. 이러한 과정을 통해 얻은 깊이영상은 다시점 영상 합성 방법을 이용하여 다시점 영상을 획득한다. 이와 같은 과정은 다중 스레드를 이용하여 빠르게 처리할 수 있도록 구현했다. 실험을 통해 두 시점의 컬러영상과 두 시점의 깊이영상이 실시간으로 획득했고, 약 7 fps의 프레임율로 10시점의 중간시점을 동시에 생성했다.

• 한국환경과학회지
• /
• 제27권7호
• /
• pp.531-541
• /
• 2018

Road freezing caused by snowfall during wintertime causes traffic congestion and many accidents. To prevent such problems, we developed, in this study, a system to predict road freezing based on weather forecast data and the freezing generation modules. The weather forecast data were obtained from a high-resolution model with 1 km resolution for Jeju Island from 00:00 KST on December 1, 2017, to 23:00 KST on February 28, 2018. The results of the weather forecast data show that index of agreement (IOA) temperature was higher than 0.85 at all points, and that for wind speed was higher than 0.7 except in Seogwipo city. In order to evaluate the results of the freezing predictions, we used model evaluation metrics obtained from a confusion matrix. These metrics revealed that, the Imacho module showed good performance in precision and accuracy and that the Karlsson module showed good performance in specificity and FP rate. In particular, Cohen's kappa value was shown to be excellent for both modules, demonstrating that the algorithm is reliable. The superiority of both the modules shows that the new system can prevent traffic problems related to road freezing in the Jeju area during wintertime.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2007년도 춘계학술발표회 논문집
• /
• pp.103-106
• /
• 2007

Recently, production and application of ortho image using high resolution image are increasing by acquired high quality data from development of photogrammetry and IT technology. Generally, An ortho image has some problems that cannot remove completely to relief displacement about cultural feature like building and overpass because of performance rectification using DEM. Therefore, in this study, I generated DSM each of four experiment cases for production of true ortho image which is removed relief displacement of building using digital photogrammetry technique and LiDAR data, presented the plan of DSM production that is appropriate to production true ortho image by analyzing an accuracy after manufacture an ortho image each of DSM.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권4호
• /
• pp.415-424
• /
• 2016

This paper describes a high data rate proximity transmitter design for high resolution smartphone-mirrored display applications. A 2 Gb/s transmitter is designed with a low transmission power of -70 dBm/MHz and a wide bandwidth of nearly 3 GHz. A digital pre-correction method is employed in the transmitter to mitigate the inter-symbol interference problem. A carrier-based digital pulse shaping and a reconfigurable digital envelope generation methods are employed for robust operation by utilizing 20 phases from a 2 GHz phase-locked loop. A 6.5-9.5 GHz transmitter implemented in 65 nm CMOS achieves the maximum data rate of 2 Gb/s, consuming only 7.6 mW from a 1 V supply.